File size: 5,705 Bytes
65784d9
 
 
ecd427f
65784d9
ecd427f
 
3806189
65784d9
 
310e819
3806189
ecd427f
 
3806189
ecd427f
 
 
 
 
 
 
 
 
 
3806189
ecd427f
3806189
 
 
 
ecd427f
 
 
65784d9
 
 
 
 
 
 
 
 
 
 
 
ecd427f
65784d9
 
ecd427f
65784d9
 
ecd427f
65784d9
 
ecd427f
310e819
 
 
 
 
 
 
 
 
ecd427f
3806189
ecd427f
3806189
 
 
 
65784d9
310e819
65784d9
 
 
 
 
 
 
 
 
 
 
ecd427f
 
 
 
3806189
 
ecd427f
3806189
 
 
 
 
 
ecd427f
3806189
 
 
 
 
 
ecd427f
 
3806189
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ecd427f
 
3806189
 
 
 
ecd427f
 
 
 
 
 
 
 
3806189
 
 
 
 
 
 
 
 
 
ecd427f
3806189
ecd427f
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
# from controlnet_aux import OpenposeDetector
# from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
# from diffusers import UniPCMultistepScheduler
import gradio as gr
# import torch
import base64
from io import BytesIO
from PIL import Image, ImageFilter
import cv2
import numpy as np

canvas_html = '<pose-maker/>'
load_js = """
async () => {
  const url = "https://huggingface.co/datasets/mishig/gradio-components/raw/main/mannequinAll.js"
  fetch(url)
    .then(res => res.text())
    .then(text => {
      const script = document.createElement('script');
      script.type = "module"
      script.src = URL.createObjectURL(new Blob([text], { type: 'application/javascript' }));
      document.head.appendChild(script);
    });
}
"""

get_js_image = """
async (canvas, prompt) => {
  const poseMakerEl = document.querySelector("pose-maker");
  const imgBase64 = poseMakerEl.captureScreenshot();
  return [imgBase64, prompt]
}
"""

# # Models
# controlnet = ControlNetModel.from_pretrained(
#     "lllyasviel/sd-controlnet-depth", torch_dtype=torch.float16
# )
# pipe = StableDiffusionControlNetPipeline.from_pretrained(
#     "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
# )
# pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)

# # This command loads the individual model components on GPU on-demand. So, we don't
# # need to explicitly call pipe.to("cuda").
# pipe.enable_model_cpu_offload()

# # xformers
# pipe.enable_xformers_memory_efficient_attention()

# # Generator seed,
# generator = torch.manual_seed(0)

low_threshold = 100
high_threshold = 200

def get_canny_filter(image):
    if not isinstance(image, np.ndarray):
        image = np.array(image) 
        
    image = cv2.Canny(image, low_threshold, high_threshold)
    image = image[:, :, None]
    image = np.concatenate([image, image, image], axis=2)
    canny_image = Image.fromarray(image)
    return canny_image

def generate_images(canvas, prompt):
    try:
        base64_img = canvas
        image_data = base64.b64decode(base64_img.split(',')[1])
        input_img = Image.open(BytesIO(image_data)).convert(
            'RGB').resize((512, 512))
        input_img = input_img.filter(ImageFilter.GaussianBlur(radius=2))
        input_img = get_canny_filter(input_img)
        # output = pipe(
        #     prompt,
        #     input_img,
        #     generator=generator,
        #     num_images_per_prompt=3,
        #     num_inference_steps=20,
        # )
        all_outputs = [input_img, input_img, input_img]
        # all_outputs.append(input_img)
        # for image in output.images:
        #     all_outputs.append(image)
        return all_outputs
    except Exception as e:
        raise gr.Error(str(e))

def placeholder_fn(axis):
    pass

js_change_rotation_axis = """
async (axis) => {
  const poseMakerEl = document.querySelector("pose-maker");
  poseMakerEl.changeRotationAxis(axis);
}
"""

js_pose_template = """
async (pose) => {
  const poseMakerEl = document.querySelector("pose-maker");
  poseMakerEl.setPose(pose);
}
"""

with gr.Blocks() as blocks:
    gr.HTML(
        """
            <div style="text-align: center; margin: 0 auto;">
              <div
                style="
                  display: inline-flex;
                  align-items: center;
                  gap: 0.8rem;
                  font-size: 1.75rem;
                "
              >
                <h1 style="font-weight: 900; margin-bottom: 7px;margin-top:5px">
                  Pose in 3D & Render with ControlNet (SD-1.5)
                </h1>
              </div>
              <p style="margin-bottom: 10px; font-size: 94%; line-height: 23px;">
                Using <a href="https://github.com/lllyasviel/ControlNet">ControlNet</a> and <a href="https://boytchev.github.io/mannequin.js/">three.js/mannequin.js</a>
              </p>
              <p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a></p>
            </div>
        """
    )
    with gr.Row():
        with gr.Column():
            canvas = gr.HTML(canvas_html, elem_id="canvas_html", visible=True)
            with gr.Row():
                rotation_axis = gr.Radio(["x", "y", "z"], value="x", label="Joint rotation axis")
                pose_template = gr.Radio(["regular", "ballet", "handstand", "split", "kick", "chilling"], value="regular", label="Pose template")
            prompt = gr.Textbox(
                label="Enter your prompt",
                max_lines=1,
                placeholder="best quality, extremely detailed",
            )
            run_button = gr.Button("Generate")
        with gr.Column():
            gallery = gr.Gallery().style(grid=[2], height="auto")
    rotation_axis.change(fn=placeholder_fn,
                            inputs=[rotation_axis],
                            outputs=[],
                            queue=False,
                            _js=js_change_rotation_axis)
    pose_template.change(fn=placeholder_fn,
                            inputs=[pose_template],
                            outputs=[],
                            queue=False,
                            _js=js_pose_template)
    run_button.click(fn=generate_images,
                     inputs=[canvas, prompt],
                     outputs=[gallery],
                     _js=get_js_image)
    blocks.load(None, None, None, _js=load_js)

blocks.launch(debug=True)